A5062965705- Machine Fault Diagnosis Techniques
- Machine Learning in Bioinformatics
- Gear and Bearing Dynamics Analysis
- Smart Grid and Power Systems
- Face and Expression Recognition
- Fault Detection and Control Systems
- Industrial Vision Systems and Defect Detection
- Structural Integrity and Reliability Analysis
- Advanced Image and Video Retrieval Techniques
- Advanced Algorithms and Applications
- Sparse and Compressive Sensing Techniques
Guangdong University of Technology
2022-2023
Guangdong-Hongkong-Macau Joint Laboratory of Collaborative Innovation for Environmental Quality
2023
Hunan University of Science and Technology
2019-2020
Adaptive sparsest narrow‐band decomposition (ASNBD) method is proposed based on matching pursuit (MP) and empirical mode (EMD). ASNBD obtains the local (LNB) components during optimization process. Firstly, an optimal filter designed. The parameter vector in obtained optimization. optimized objective function a regulated singular linear operator so that each component limited to be LNB signal. Afterward, generated by filtering original signal with filter. Compared MP, superior both physical...
The detection of high voltage permanent magnet motors has always been a big problem due to the interference and magnetic field on diagnosis. Especially magenetic tile motor, failure will directly lead operation motor. We propose Multi-view Unsupervised Consistent Soft-label Feature Selection(MUCSFS). This method constructed consistent pseudo-labels through soft labels clustering affinity each view sample model by integrating selection constraints into mapping model. is used filter fault data...
Adaptive sparsest narrow-band decomposition is the most sparse solution to search for signals in over-complete dictionary library containing intrinsic mode functions, which transform signal into an optimization problem, but calculation accuracy must be improved case of strong noise interference. Therefore, combination with algorithm complementary ensemble empirical decomposition, a new method adaptive obtained. In white opposite paired symbol added target reduce reconstruction error and...
Abstract Image‐based scheme has attracted wide attention in the fault detection of high‐voltage permanent magnet motors, but it often suffers from shooting conditions. Multiview feature selection allows multisource information to be fused, which can improve accuracy and robustness image detection. Therefore, we propose multiview unsupervised consistency via soft‐label (MUCSFS). This method constructs consistent pseudo labels through soft clustering affinity each view sample builds model by...
Non-negative matrix factorization (NMF) is a widely used technique for dimensionality reduction, and generalized separable NMF (GSNMF) can learn the representation with better interpretability, as it decomposes given based on row features column at same time. But in some cases, GSNMF algorithm faces 0- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> problem, where only one perspective of feature be developed. This paper modified...